50 resources related to Image Synthesis
- Topics related to Image Synthesis
- IEEE Organizations related to Image Synthesis
- Conferences related to Image Synthesis
- Periodicals related to Image Synthesis
- Most published Xplore authors for Image Synthesis
No organizations are currently tagged "Image Synthesis"
The conference program will consist of plenary lectures, symposia, workshops and invitedsessions of the latest significant findings and developments in all the major fields of biomedical engineering.Submitted papers will be peer reviewed. Accepted high quality papers will be presented in oral and postersessions, will appear in the Conference Proceedings and will be indexed in PubMed/MEDLINE
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020)
The IEEE International Symposium on Biomedical Imaging (ISBI) is the premier forum for the presentation of technological advances in theoretical and applied biomedical imaging. ISBI 2020 will be the 17th meeting in this series. The previous meetings have played a leading role in facilitating interaction between researchers in medical and biological imaging. The 2020 meeting will continue this tradition of fostering cross-fertilization among different imaging communities and contributing to an integrative approach to biomedical imaging across all scales of observation.
The International Conference on Image Processing (ICIP), sponsored by the IEEE SignalProcessing Society, is the premier forum for the presentation of technological advances andresearch results in the fields of theoretical, experimental, and applied image and videoprocessing. ICIP 2020, the 27th in the series that has been held annually since 1994, bringstogether leading engineers and scientists in image and video processing from around the world.
Multimedia technologies, systems and applications for both research and development of communications, circuits and systems, computer, and signal processing communities.
The ICASSP meeting is the world's largest and most comprehensive technical conference focused on signal processing and its applications. The conference will feature world-class speakers, tutorials, exhibits, and over 50 lecture and poster sessions.
No periodicals are currently tagged "Image Synthesis"
2019 27th Signal Processing and Communications Applications Conference (SIU), 2019
In this study, we compare deep learning methods for generating images of handwritten characters. This problem can be thought of as a restricted Turing test: A human draws a character from any desired alphabet and the system synthesizes images with similar appearances. The intention here is not to merely duplicate the input image but to add random perturbations to give ...
2019 Chinese Control And Decision Conference (CCDC), 2019
In order to solve the problem that it is difficult to obtain fire image data in CNN training, this paper discusses the method of generating fire image by means of generative adversarial networks. How to generate the desired fire image according to the known observation variables is discussed. According to the structure of InfoGAN and ACGAN, a GAN structure for ...
IEEE Photonics Journal, 2010
This paper presents a novel camera simulation framework capable of simulating the optical path of a variety of camera systems through the technique of Monte Carlo Path tracing. Path tracer is a ray-tracing technique that uses Markov chains to solve the global illumination problem, i.e., the problem of calculating the distribution of light in an environment, taking into account all ...
2019 16th Conference on Computer and Robot Vision (CRV), 2019
In this paper, we present a novel Hierarchically-fused Generative Adversarial Network (HfGAN) for synthesizing realistic images from text descriptions. While existing approaches on this topic have achieved impressive success, to generate 256×256 images from captions, they commonly resort to coarse-to-fine scheme and associate multiple discriminators in different stages of the networks. Such a strategy is both inefficient and prone to ...
2019 IEEE International Conference on Multimedia and Expo (ICME), 2019
Manipulating person images under diverse poses, which transfers a person from one pose to another desired pose, is an interesting yet challenging task due to large non-rigid spatial deformation. Most existing works fail to preserve the fine-grained appearance consistency along with the pose changes due to the lack of explicit constraints and spatial modeling, leading to unrealistic results with severe ...
P2020 Establishing Image Quality Standards for Automotive
Hamid R Tizhoosh - Fuzzy Image Processing
Fast Broadband Impedance Matching with Automatic Circuit Synthesis: MicroApps 2015 - Keysight Technologies
Dario Floreano: The Evolutionary Analysis & Synthesis of Intelligent Living Systems
IBM Researcher Dr. Jamie Garcia Explores Sustainable Polymers at Rising Stars 2016
Solving Sparse Representation for Image Classification using Quantum D-Wave 2X Machine - IEEE Rebooting Computing 2017
Zohara Cohen AMA EMBS Individualized Health
Broadband IQ, Image Reject, and Single Sideband Mixers: MicroApps 2015 - Marki Microwave
IEEE Low-Power Image Recognition Challenge (LPIRC)
Synthesis and Selection of High Priority Areas - ETAP Delhi 2016
Nanotechnology, we are already there: APEC 2013 KeyTalk with Dr. Terry Lowe
Q&A with Ryan Dailey: IEEE Rebooting Computing Podcast, Episode 12
Tapping the Computing Power of the Unconscious Brain
CPIQ Update and the Case for Image Quality Standards in Automotive
Welcome: Low Power Image Recognition Challenge
Low Power Image Recognition: The Challenge Continues
My Computer Speaks Colors! Fuzzy Color Spaces for Image Understanding, Description and Retrieval
Robotics History: Narratives and Networks Oral Histories: Ray Jarvis
Robotics History: Narratives and Networks Oral Histories: Minoru Asada
In this study, we compare deep learning methods for generating images of handwritten characters. This problem can be thought of as a restricted Turing test: A human draws a character from any desired alphabet and the system synthesizes images with similar appearances. The intention here is not to merely duplicate the input image but to add random perturbations to give the impression of being human-produced. For this purpose, the images produced by two different generative models (Generative Adversarial Network and Variational Autoencoder) and the related training method (Reptile) are examined with respect to their visual quality in a subjective manner. Also, the capability of transferring the knowledge that is obtained by the model is challenged by using different datasets for the training and test processes. Using the proposed model and meta-learning method, it is possible to produce not only images similar to the ones in the training set but also novel images that belong to a class which is seen for the first time.
In order to solve the problem that it is difficult to obtain fire image data in CNN training, this paper discusses the method of generating fire image by means of generative adversarial networks. How to generate the desired fire image according to the known observation variables is discussed. According to the structure of InfoGAN and ACGAN, a GAN structure for generating fire image is proposed. Fire area is selected as a known observation variable to generate the corresponding fire image. Experiments show that the network structure can generate the required images according to the values of a observed variables. And the quality of the generated image is related to the distribution of observed variables in the data set.
This paper presents a novel camera simulation framework capable of simulating the optical path of a variety of camera systems through the technique of Monte Carlo Path tracing. Path tracer is a ray-tracing technique that uses Markov chains to solve the global illumination problem, i.e., the problem of calculating the distribution of light in an environment, taking into account all forms of scattering, absorption, and interreflection. In global illumination, we deal with the interaction of light that reaches a surface directly from a light source (direct lighting) as well as the interaction of light that reaches a surface as a result of scattering or transmission from or through other objects (indirect lighting). Available pieces of ray-tracer software use very simple models for their camera system like the pinhole camera, the thin-lens camera, and the thick-lens camera. The novelty and strength of our simulation tool is the capability to simulate any arbitrary and complex camera system. Any kind of optical component (like mirrors, prisms, and optical filters) can be placed inside the camera system or on the image sensor, and the tool synthesizes the image taken by that complex camera system, which can be used to optimize the parameters of the system for a specific application. The tool was used to simulate the optical path of a variety of passive depth recovery systems (like stereoscopy, Plenoptic Camera, and Bi-prism camera) that are included in this paper.
In this paper, we present a novel Hierarchically-fused Generative Adversarial Network (HfGAN) for synthesizing realistic images from text descriptions. While existing approaches on this topic have achieved impressive success, to generate 256×256 images from captions, they commonly resort to coarse-to-fine scheme and associate multiple discriminators in different stages of the networks. Such a strategy is both inefficient and prone to artifacts. Motivated by the above findings, we propose an end-to-end network that can generate 256×256 photo-realistic images with only one discriminator. We fully exploit the hierarchical information from different layers and directly generate the fine-scale images by adaptively fusing features from multi- hierarchical layers. We quantitatively evaluate the synthesized images with Inception Score, Visual-semantic Similarity and average training time on the CUB birds, Oxford-102 flowers, and COCO datasets. The results show that our model is more efficient and noticeably outperforms the previous state-of-the- art methods.
Manipulating person images under diverse poses, which transfers a person from one pose to another desired pose, is an interesting yet challenging task due to large non-rigid spatial deformation. Most existing works fail to preserve the fine-grained appearance consistency along with the pose changes due to the lack of explicit constraints and spatial modeling, leading to unrealistic results with severe artifacts. In this paper, we propose a novel Part- Preserving Generative Adversarial Network (PP-GAN) to achieve good manipulation quality by explicitly enforcing rich structure constraints over generative modeling. PP-GAN is proposed to decompose the challenging spatial transformation of the whole body into fine-grained part-level transformations, which are then integrated via human joint structure constraint. Given arbitrary poses, PP-GAN integrates human joint structure and region-level part cues as inputs to perform explicit generative modeling. Besides, we introduce a parsing-consistent loss to enforce semantic consistency among images with diverse poses, which guides the image synthesis from a semantic perspective. Extensive qualitative and quantitative evaluations on two benchmarks show that our PP-GAN significantly outperforms the state-of-the-art baselines in generating more realistic and plausible image synthesis results. PP-GAN successfully preserves part-level characteristics even for most challenging pose changes while prior works are easy to fail.
We propose an approach for digitally altering people's outfits in images. Given images of a person and a desired clothing style, our method generates a new clothing item image. The new item displays the color and pattern of the desired style while geometrically mimicking the person's original item. Through superimposition, the altered image is made to look as if the person is wearing the new item. Unlike recent works with full-image synthesis, our work relies on segment synthesis, yielding benefits in virtual try-on. For the synthesis process, we assume two underlying factors characterizing clothing segments: geometry and style. These two factors are disentangled via preprocessing and combined using a neural network. We explore several networks and introduce important aspects of the architecture and learning process. Our experimental results are three-fold: (1) on images from fashion-parsing datasets, we demonstrate the generation of high-quality clothing segments with fine-level style control; (2) on a virtual try-on benchmark, our method shows superiority over prior synthesis methods; (3) in transferring clothing styles, we visualize the differences between our method and neural style transfer.
Photographic image synthesis is a new research focus in the field of deep learning, which uses the known image description information to generate the image approaching to the real scene. In this paper, a novel photographic image synthesis method based on the highway residual U-net (HRU) is proposed. The proposed highway residual blocks (HRBs) are embedded between the levels of the U-net and the proposed HRBs effectively filter the information transmitted by each level of the U-net and speed up the convergence of the network. In addition, the resize-convolution layers in HRU are used to replace the deconvolution layers to reduce the checkerboard artifacts in the synthesized images. HRU can be trained end-to-end with the image description map and the corresponding photographic image. Extensive experiments on Cityscapes dataset and GTA5 dataset demonstrate that images synthesized by the presented approach are considerably more realistic than other synthetic approaches.
Recent years have witnessed the unprecedented success in single image synthesis by the means of convolutional neural networks (CNNs). High-level synthesis of facial image such as expression translation and attribute swap is still a challenging task due to high non-linearity. Previous methods suffer from the limitations that being unable to transfer multiple face attributes simultaneously, or incapability of transferring an attribute to another by a continuously changing way. To address this problem, we propose a two- discriminator adversarial autoencoder network (TAAN). The latent-discriminator is trained to disentangle an input image from its original facial attribute, while the pixel-discriminator is trained to make the output image attach to the target facial attribute. By controlling the attribute values, we can choose which and how much a specific attribute can be perceivable in the generated image. Quantitative and qualitative evaluations are conducted on the celebA and KDEF datasets, and the comparison with the state-of-the-art methods shows the competency of our proposed TAAN.
Large-scale dataset plays a key role in the driving scene understanding for deep learning based-autonomous driving tasks. Due to the fact that the annotation for a large number of images is extremely labor-intensive and time- consuming, many researchers turn to using image-synthesis techniques for automatic construction of training data. However, traditional methods often have difficulties in producing high-definition driving scene images. To tackle this problem, in this paper, we propose a novel deep model - hdCGAN - for high-definition image-to-image translation. The hdCGAN is built on a conditional GAN in combination with a spectral normalization. Moreover, we improve the hdCGAN by using a stacked network architecture and the enhanced model is called stack-hdCGAN. With the guidance of multi-scale discriminators and the constraint of spectral normalization in the training procedure, the learned models can generate high-resolution and high-quality driving scene images from corresponding semantic segmentation maps. Quantitative and qualitative evaluations on the Cityscapes dataset demonstrate the effectiveness of the proposed models.
Image style transfer has attracted much attention from many fields and received promising performance. However, style transfer in the cross-domain field, e.g., the transfer between near-infrared and visible light images, is rarely studied. In the cross-domain image style transfer, one key issue is mismatching problem existing in the generated semantic regions. In this paper, we propose a novel model of Semantic GAN, which integrates the semantic guidance and the recent CycleGAN. In particular, we present a semantic style loss with Gram matrix to well preserve the semantic information in the generated images. The proposed Semantic GAN can control the transfer in the right way with semantic masks and solve the mismatching problem. We apply our approach to two outdoor scene datasets to evaluate the performance of all competing methods. The experimental results show that our approach outperforms previous methods in addressing the mismatching problem and providing a good quality result.
No standards are currently tagged "Image Synthesis"